Unsupervised Learning of the Total Variation Flow

Tamara G. Grossmann, Sören Dittmer, Yury Korolev, Carola-Bibiane Schönlieb

Research output: Working paper / PreprintPreprint

1 Downloads (Pure)

Abstract

The total variation (TV) flow generates a scale-space representation of an image based on the TV functional. This gradient flow observes desirable features for images such as sharp edges and enables spectral, scale, and texture analysis. The standard numerical approach for TV flow requires solving multiple non-smooth optimisation problems. Even with state-of-the-art convex optimisation techniques, this is often prohibitively expensive and strongly motivates the use of alternative, faster approaches. Inspired by and extending the framework of physics-informed neural networks (PINNs), we propose the TVflowNET, a neural network approach to compute the solution of the TV flow given an initial image and a time instance. We significantly speed up the computation time by more than one order of magnitude and show that the TVflowNET approximates the TV flow solution with high fidelity. This is a preliminary report, more details are to follow.
Original languageEnglish
Publication statusPublished - 9 Jun 2022

Keywords

  • cs.CV
  • cs.LG
  • eess.IV

Fingerprint

Dive into the research topics of 'Unsupervised Learning of the Total Variation Flow'. Together they form a unique fingerprint.

Cite this